检索结果-内蒙古大学图书馆

Predicting host-pathogen interactions with machine learning algorithms: A scoping review

INFECTION GENETICS AND EVOLUTION 2025年 130卷 105751页

作者： Sahragard, Rasool Arabfard, Masoud Najafi, Ali Baqiyatallah Univ Med Sci Biomed Technol Inst Mol Biol Res Ctr Tehran Iran Baqiyatallah Univ Med Sci Syst Biol & Poisonings Inst Chem Injuries Res Ctr Tehran Iran

Background: Diseases caused by pathogenic microorganisms pose a persistent global health challenge. Pathogens exploit host mechanisms through intricate molecular interactions. Understanding these host-pathogen interactions (HPIs), particularly protein-protein interactions (PPIs), is crucial for developing therapeutic strategies. While experimental approaches are essential, they are often labor-intensive and costly. Researchers have been able to predict HPIs more efficiently due to recent advances in artificial intelligence and machine learning. However, existing reviews lack a systematic evaluation of different machine learning methodologies and their effectiveness. Methods: This scoping review critically examines recent studies on machine learning-based Host-Pathogen Interaction (HPI) prediction, categorizing them by host and pathogen types, machine learning algorithms, and key evaluation metrics. The methodology is based on the study beginning with a preliminary search in reputable using key phrases related to host-pathogen interactions from 2019 to 2024. This process yielded 46 relevant articles, from which 30 were selected for review after evaluating titles and abstracts. Results: Our findings indicate that tree-based algorithms, particularly Random Forest and Gradient Boosting, are the most prevalent in Host-Pathogen Interaction (HPI) prediction. The filter articles were categorized by host and pathogen type and further subdivided into four subcategories based on the prediction type and machine learning algorithms: classic, tree-based, vector-based, and neural network algorithms. Convolutional and recurrent neural networks are among the deep learning models that demonstrate promising accuracy, but they require a lot of labeled data for effective training. Additionally, the analysis uncovers significant gaps in dataset standardization and model interpretability, which pose challenges to the broader applicability of these predictive models. Conclusion: In this re

关键词： Host-pathogen interactions Protein-protein interaction Prediction algorithms machine learning algorithms Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Applying machine learning algorithms to explore the impact of combined noise and dust on hearing loss in occupationally exposed populations

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-10页

作者： Li, Yong Sun, Xin Qu, Yongtao Yang, Shuling Zhai, Yueyi Qu, Yan Hebei Med Univ Dept Otolaryngol Shijiazhuang Peoples R China Hebei Gen Hosp Dept Otolaryngol Shijiazhuang Peoples R China Hebei North Univ Zhangjiakou Peoples R China Hebei Med Univ Anim Lab Hosp 3 Shijiazhuang Peoples R China Hebei Med Univ Dept Otolaryngol Hosp 3 Shijiazhuang Peoples R China

This study aimed to explore the combined impacts of occupational noise and dust on hearing and extra-auditory functions and identify associated risk factors via machine learning techniques. Data from 14,145 workers (627 with occupational noise-induced hearing loss (ONIHL)) at Hebei Medical Examination Center (2017-2023) were analyzed. Workers with combined exposure and without specific contraindications or other hearing impairment causes were included. Demographic and clinical data were gathered. Chi-square and Mann-Whitney U tests examined variables, and multivariate logistic regression determined ONIHL risk factors. machine learning algorithms like Logistic Regression and Random Forest were developed, optimized, and evaluated. Results showed significant differences in gender, exposure, blood pressure, smoking, etc. between ONIHL and non-ONIHL groups. Male gender, combined exposure, diastolic blood pressure elevation, smoking, fasting blood glucose elevation, and age were positive predictors, while systolic blood pressure elevation was negative. The logistic model had the highest predictive ability (ROC = 0.714). Subgroup analysis revealed a significant positive correlation in specific subgroups. In summary, combined exposure increased ONIHL risk and affected health. machine learning effectively predicted ONIHL, but the study had limitations and needed further research.

关键词： Occupational exposure Noise and dust Hearing loss machine learning algorithms Risk factors

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Network in Remote Sensing-Based Climate Detection Using machine learning algorithms

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 400-408页

作者： Srinivas, Jhade Raju, Ch VV Narasimha Sasikala, C. Bhaskar, Parumanchala Panyala, Amarendra Reddy Priya, Divya Department of Computer Science and Engineering - Data Science K G Reddy College of Engineering and Technology Moinabad Telangana Hyderabad India Information Technology Marri Laxman Reddy Institute of Technology and Management Dundigal Telangana Hyderabad 500043 India Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Santhiram Engineering College Nandyal India Department of Computer Science and Engineering (Data Science) Malla Reddy University Telangana Hyderabad India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Effective monitoring of the environment over a large area will require mobilization of a considerable amount of information. Otherwise, the use of traditional methods will prove to be costly and would take up so much time. Also, assessing the land cover changes between two times is one of the other methods which can be adopted to measure the environmental sustainability. Using ML techniques for predictive modeling in remote sensing has emerged as a useful approach in solving some of the environmental and climatic challenges. This research proposes a novel method in remote sensing image-based climate detection utilizing cloud computing and machine learning algorithms. Here, the cloud computing module is used in the collection of remote sensing images for the detection of climate changes. Then, the collected image is processed for noise removal as well as normalization. The processed image is segmented, and features are extracted utilizing a fuzzy K-clustering-based contour Gaussian model with graph cut Boltzmann CNN. Experimental analysis is carried out for various remote sensing-based climate change datasets in terms of training accuracy, random precision, AUC, recall, and F-measure. The proposed technique obtained 97% of training accuracy, 95% of random precision, 96% of recall, 93% of AUC, and 94% of F-measure. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Climate detection Cloud computing Contour Gaussian model machine learning algorithms Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Sex classification accuracy through machine learning algorithms - morphometric variables of human ear and nose

引用

BMC RESEARCH NOTES 2025年第1期18卷 1-10页

作者： Kaur, Tej Krishan, Kewal Sharma, Akanksha Guleria, Ankita Sharma, Vishal Panjab Univ Inst Forens Sci & Criminol Chandigarh India Panjab Univ UGC Ctr Adv Study Dept Anthropol Sect 14 Chandigarh India

ObjectiveSex determination is an important parameter for personal identification in forensic and medico-legal examinations. The study aims at predicting sex accuracy from different parameters of ear and nose by using a novel approach of machine learning Library, 'PyCaret'.ResultsThe present research was carried out on 508 participants (264 males and 244 females) aged 18-35 years from north India. Various ear and nose measurements were recorded on each participant. PyCaret employs a train-eval-testing validation approach, yielding a comprehensive output of the model in the form of a table that consolidates the average scores of all models over ten folds, including the respective time values. These models were compared based on performance metrics, and time taken. The logistic regression classifier emerged as the top-performing model, achieving the highest scores of 86.75% for sex prediction accuracy. Nasal breadth has been concluded as the most significant variable in accurate sex prediction. The findings indicate that the majority of the ear and nose characteristics significantly contribute to sexual dimorphism. This novel approach for sex classification can be efficiently used in a variety of forensic examinations and crime scene investigation especially where there is a need for estimation of sex for personal identification.

关键词： Human anatomy and morphology Ear and nose morphology Forensic identification machine learning algorithms PyCaret Sex classification

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms for Autonomous Underwater Vehicle (AUV) Navigation

Machine Learning Algorithms for Autonomous Underwater Vehicl...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Upma Jain Nandini Shirish Boob Munugapati Bhavana Yogendra Kumar Archana Sehgal Anandhi R J Department of Comp. Sc. & Engg. Graphic Era Deemed to be University Dehradun Saveetha School of EngG. Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of Comp. Sc. & Engg MLR Institute of Technology Hyderabad Telangana Department of Electrical Engg. GLA University Mathura India Department of Comp. Sc. & Engg. Lovely Professional University Phagwara India Department of Information Science Engineering New Horizon College of Engineering Bangalore

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Autonomous underwater vehicles (AUVs) play an extremely important role in the fields of oceanography, marine science and underwater infrastructure assessment. Of course, underwater navigation isn't easy either due to varying ocean currents, limited vision, and there's no GPS. This article uses machine learning techniques to describe how AUV navigation can be improved in underwater environments with unknown environment, then enable more reliable decision making and real time obstacle avoidance. This thesis investigates many ML approaches for route planning, sensor data fusion, and obstacle detection including supervised, unsupervised learning and reinforcement learning. With great significance, reinforcement learning algorithms can optimize trial and error learning based navigation techniques to be adapted to novel situations. Additionally, deep leaning algorithms combined with data from sensors such as sonar and cameras are able to enable precise underwater landscape perception and mapping. We apply these algorithms to virtual and physical AUV missions and demonstrate that they result in significant increases in navigation precision, energy efficiency, and mission time. This research's careful consideration of the potential of machine learning for transforming AUV navigation makes more intelligent and autonomous underwater operations possible in many marine sectors.

关键词： Autonomous underwater vehicles machine learning algorithms Scalability Transportation Reinforcement learning Sonar navigation Real-time systems Planning Oceanography Internet of Things

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms for Forecasting Air Quality Index: A Predictive Analysis in the Taj Trapezium Zone (TTZ) of Agra

Machine Learning Algorithms for Forecasting Air Quality Inde...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Swati Varshney Jitendra Nath Shrivastava Neha Gupta Invertis University Bareilly U.P India Department of CSE Invertis University Bareilly U.P India Symbiosis University of Applied Science Indore M.P India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Clean air is vital for sustaining life, and its quality directly impacts health. As industrialization progresses and populations grow, air pollution has become increasingly prevalent, emerging as a significant societal challenge. Air pollution has wide-ranging negative impacts on human health, including increased risk of early death and various ailments such as skin irritation., pulmonary infections, respiratory ailments, pneumonia, lung cancer, and cardiac complications. The purpose of this study is to use machine learning algorithms to predict the Taj Trapezium Zone’s air quality index.. Such predictions can inform preventive action to mitigate air pollution. The study compares four algorithmic approaches: Light Gradient Boosting machine (LightGBM), categorical boosting (Catboost), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost). These algorithm’s performance is evaluated based on several parameters, including R-SQUARE, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and ((MAE).

关键词： machine learning algorithms Urban areas Lung cancer Predictive models Boosting Prediction algorithms Air pollution Market research Indexes Forecasting

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms Based on Variations of the Least Squares Method for Power Amplifier Distortion Compensation

Machine Learning Algorithms Based on Variations of the Least...

引用

Systems of Signals Generating and Processing in the Field of on Board Communications

作者： Igor V. Komarov Svetlana F. Gorgadze Moscow Technical University of Communications and Informatics Moscow Russia

ISBN: (数字)9798331532635

ISBN: (纸本)9798331532642

Variants of indirect learning based on the Least Squares Method (LSM) and the Recursive Least Squares Method (RLSM) are considered for digital predistortion of nonlinear distortions in complex composite signals with high peak-toaverage power ratios in power amplifiers. The advantage of the recursive algorithm is identified, providing approximately 9 dB lower levels of spurious out-of-band emissions for the amplified complex signal compared to the simple least squares algorithm. It is shown that for the polynomial model of the power amplifier used in the study, the recursive algorithm requires approximately 700 times more elementary mathematical operations to achieve the most efficient compensation of signal nonlinearities than the least squares algorithm.

关键词： machine learning algorithms Nonlinear distortion Computer architecture Approximation algorithms Predistortion Polynomials Mathematical models Hardware Least mean squares methods Convergence

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms for Dynamic Financial Management and Fraud Detection: Implementing Anomaly Detection, and Risk Assessment Techniques

Machine Learning Algorithms for Dynamic Financial Management...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： T Haripriya S. Chandramouli M. Kavitha Malathi Devi Parne Desini Srinivas B Kiran Bala Department of Finance Vignana Jyothi Institute of Management Hyderabad India Reah School of Business Management Approved by AICTE Affiliated to Osmania University Hyderabad India Siddhartha Institute of Computer Sciences India Aurora's PG College(MCA) Hyderabad India ManPower Development College Hyderabad India Department of AI & DS K. Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Ensuring security and identifying fraudulent activity have become critical concerns in an era where financial transactions are increasingly conducted digitally. There is a need to enhance the efficacy of the existing fraud detection systems, which requires the application of mainly the higher order machine learning algorithms. This study explores a hybrid approach that blends autoencoder-based anomaly detection with XGBoost classification. By computing reconstruction losses, the autoencoder is used to detect departures from typical transaction patterns. The proposed model is implemented using python software. The XGBoost model further refines this approach by classifying transactions based on features derived from the autoencoder and additional transaction attributes. The hybrid model achieves an accuracy of 99%. These outcomes demonstrate how well and quickly the hybrid model can identify fraudulent transactions while reducing errors. By improving overall system performance and adjusting to changing fraud tactics, this method provides a notable breakthrough in financial fraud detection.

关键词： machine learning algorithms Computational modeling System performance Autoencoders Software Fraud Security Risk management Anomaly detection Python

来源：评论

学校读者我要写书评

暂无评论

Non-enzymatic electrochemical sensors using Polyaniline:Metal orotate nanocomposites for selective dopamine and glucose detection: Predicting sensor performance with machine learning algorithms

引用

MATERIALS SCIENCE IN SEMICONDUCTOR PROCESSING 2025年 193卷

作者： Yildiz, Dilber Esra Tasaltin, Nevin Baytemir, Guelsen Gursu, Gamze Karakus, Selcan Yildirim, Tugrul Sahin, Yesim Muge Kucukdeniz, Tarik Kose, Dursun Ali Hitit Univ Dept Phys Corum Turkiye Maltepe Univ Environm & Energy Technol Res Ctr Istanbul Turkiye Maltepe Univ Dept Renewable Energy Tech & Management Istanbul Turkiye Maltepe Univ Dept Basic Sci Istanbul Turkiye Maltepe Univ CONSENS Inc Technopark Istanbul Res Ctr Istanbul Turkiye Maltepe Univ Dept Elect & Elect Engn Istanbul Turkiye Istanbul Univ Cerrahpasa Dept Chem Istanbul Turkiye Hitit Univ Vocat Sch Tech Sci Occupat Hlth & Safety Program TR-19030 Corum Turkiye Arel Univ Arel Potkam Istanbul Turkiye Hlth Biotechnol Joint Res & Applicat Ctr Excellenc TR-34220 Istanbul Turkiye Istanbul Univ Cerrahpasa Fac Engn Dept Ind Engn TR-34320 Istanbul Turkiye Hitit Univ Dept Chem Corum Turkiye

In this study, we developed novel non-enzymatic electrochemical biosensors, capitalizing on the capabilities of orotate metal complexes encompassing Co(II), Cu(II), Ni(II), and Zn(II) cations coordinated within polyaniline (PANI) nanocomposites (NCs). Our approach involved the meticulous crystallization of metal cation complexes from solution, utilizing orotic acid as a ligand. Through the utilization of a cost-efficient and uncomplicated sonication technique, we synthesized PANI:Co(II), PANI:Ni(II), PANI:Cu(II), and PANI:Zn(II) orotate NCs. Our results demonstrated that the PANI:Zn(II) orotate NCs-based sensor exhibited the highest sensitivity, recording 99.25 mu A cm- 2 mu M- 1 for dopamine detection, with a remarkable limit of detection (LOD) of 0.74 mu M. Furthermore, the sensor effectively detected glucose with a sensitivity of 24.39 mu Acm- 2mM-1 and a LOD of 1.89 mM. Importantly, the sensor displayed exceptional selectivity towards dopamine. To further enhance the sensor performance, machine learning algorithms were applied to analyze and predict the sensor's output. Models such as Linear Regression and Artificial Neural Networks (ANN) were employed to interpret the electrochemical results and predict performance metrics like sensitivity and selectivity. The outcomes of our sensor assessments underscore the potential of the PANI:Zn(II) orotate NCs as a robust platform for dopamine detection applications. Our findings provide insights for improving PANI: Zn(II) orotate NCs in biosensing. PANI:metal orotate NCs function as semiconductor materials, with sensor sensitivity closely tied to their conductance, conductivity, and impedance.

关键词： Orotate Semiconductor materials machine learning algorithms Dopamine Glucose

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on machine learning algorithms for Breast Cancer Diagnosis

引用

Procedia Computer Science 2025年 259卷 1994-2003页

作者： Hemali Shah Smita Agrawal Parita Oza Sudeep Tanwar Department of Computer Science and Engineering Nirma University Ahmedabad-382481 India

Breast Cancer (BC) is the second most found cancer in women worldwide. Different symptoms to identify breast tumors are pain in the breast, lumps, and a change in skin color and texture. In this study, we used mammograms for Breast cancer classification. The radiologist uses computer-aided diagnosis tools for a second opinion diagnosis. Nowadays, machine learning algorithms are used for the advancement of technology. The proposed research mainly focuses on machine learning classification algorithms for classifying data as benign and malignant. The datasets used are MIAS and Wisconsin for Breast cancer classification. The algorithms used are Logistic Regression, Naive Bays classifier, Support Vector machine, Decision tree, and Random Forest. Augmentation was applied to increase the size of the MIAS dataset. The performance of different classifiers is compared using measures like accuracy, precision, recall, and F-measure. Results show that for the MIAS dataset, Random forest gives the highest accuracy of 0.73 compared to all other algorithms. For the Wisconsin dataset, Logistic regression out-performs with 96.49 per cent accuracy in classifying the data.

关键词： machine learning algorithms supervised learning Breast cancer classification Mammograms MIAS Wisconsin

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：